ANLI Benchmark

Explore score history ↗

ANLI is an AI benchmark in the Benchmark Radar catalog.

Released: 2019-11-01
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

ANLI results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
InfoBERT	—	75.0	—	evidence
PaLM 2-L	—	73.1	—	evidence
RoBERTa	—	72.4	—	evidence
T0-11B	—	75.6	—	evidence
T5-3B	—	81.8	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite ANLI?

ANLI